首页期刊导航|Robotics & Machine Learning Daily News
期刊信息/Journal information
Robotics & Machine Learning Daily News
NewsRx
Robotics & Machine Learning Daily News

NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News
正式出版
收录年代

    Findings on Machine Learning Reported by Investigators at University of Connecticut (Leveraging Past Information and Machine Learning To Accelerate Land Disturbance Monitoring)

    38-39页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators publish new report on Ma chine Learning. According to news reportingoriginating from Storrs, Connecticut , by NewsRx correspondents, research stated, “Near real -time (NRT)monitoring o f land disturbances holds great importance for delivering emergency aid, mitigat ing negativesocial and ecological impacts, and distributing resources for disas ter recovery. Many past NRT techniqueswere built upon examining the overall cha nge magnitude of a spectral anomaly with a predefined threshold,namely the unsu pervised approach.”Financial support for this research came from USGS-NASA Landsat Science Team (LS T) Program.Our news editors obtained a quote from the research from the University of Conne cticut, “However,their lack of fully considering spectral change direction, cha nge date, and pre-disturbance conditions oftenled to low detection sensitivity and high commission errors, especially when only a few satellite observationswe re available at the early disturbance stage, eventually resulting in a longer la g to produce a reliabledisturbance map. For this study, we developed a novel su pervised machine learning approach guided byhistorical disturbance datasets to accelerate land disturbance monitoring. This new approach consistedof two phase s. For the first phase, the supervised approach applied retrospective analysis o n historicalHarmonized Landsat Sentinel-2 (HLS) datasets from 2015 to 2021, com bined with several open disturbanceproducts. The disturbance model was construc ted for each condition of consecutive anomaly number,with the aim of enhancing the specificity for delineating early-stage disturbance regions. Then, these stage-based models were applied for an NRT scenario to predict disturbance probabil ities with 2022 HLSimages incrementally on a weekly basis. To demonstrate the c apability of this new approach, we developedan operational NRT system incorpora ting both the unsupervised and supervised approach. Latency andaccuracy were ev aluated against 3000 samples that were randomly selected from the five most infl uentialdisturbance events of the United States in 2022, based on labels and dis turbance dates interpreted fromdaily PlanetScope images. The evaluation showed that the supervised approach required 15 days (sincethe start of the disturbanc e event) to reach the plateau of its F1 curve (where most disturbance pixels aredetected with high confidence), seven days earlier with roughly 0.2 F1 score im provement compared to theunsupervised approach (0.733 vs. 0.546 F1 score). Furt her analysis showed the improvement was mainlydue to the substantial decrease i n commission errors (17.7% vs 44.4%). The latency com ponent analysisillustrated that the supervised approach only took an average of 4.1 days to yield the first disturbance alertat its fastest daily updating spe ed, owing to its decreased sensitivity lag.”
      原文链接:
    • NETL
    • NSTL

    Reports from Macau University of Science & Technology Highlight Recent Findings in Artificial Intelligence (Artificial Intelligence Algorithms In Unmanned Surface Vessel Task Assignment and Path Planning: a Survey)

    39-40页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews - Researchers detail new data in Artificial Intelli gence. According to news reporting originating fromMacau, People’s Republic of China, by NewsRx correspondents, research stated, “Due to the complexenvironmen t and variable demands, unmanned surface vessel (USV) task assignment and path p lanninghave received much attention from academia and industry in recent years. Artificial intelligence technologiesare increasingly adopted for solving the U SV task assignment and path planning problems.”Financial supporters for this research include Zhuhai Industry-University-Resear ch Project withHongkong and Macao, Science and Technology Development Fund (FDC T) , Macau SAR, NationalNatural Science Foundation of China (NSFC), Guangdong B asic and Applied Basic Research Foundation.
      原文链接:
    • NETL
    • NSTL

    China University of Mining and Technology Reports Findings in Machine Learning (General Model for Predicting Response of Gas-Sensitive Materials to Target Gas B ased on Machine Learning)

    40-41页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Machine Learning is th e subject of a report. According to newsreporting originating in Jiangsu, Peopl e’s Republic of China, by NewsRx journalists, research stated, “Gassensors play a crucial role in various industries and applications. In recent years, there h as been anincreasing demand for gas sensors in society.”The news reporters obtained a quote from the research from the China University of Mining andTechnology, “However, the current method for screening gas-sensiti ve materials is time-, energy-, andcost-consuming. Consequently, an imperative exists to enhance the screening efficiency. In this study,we proposed a collabo rative screening strategy through integration of density functional theory and machine learning. Taking zinc oxide (ZnO) as an example, the responsiveness of Zn O to the target gas wasdetermined quickly on the basis of the changes in the el ectronic state and structure before and after gasadsorption. In this work, the adsorption energy and electronic and structural characteristics of ZnO afterads orbing 24 kinds of gases were calculated. These computed features served as the basis for training amachine learning model. Subsequently, various machine learn ing and evaluation algorithms were utilizedto train the fast screening model. T he importance of feature values was evaluated by the AdaBoost,Random Forest, an d Extra Trees models. Specifically, charge transfer was assigned importance valu esof 0.160, 0.127, and 0.122, respectively, ranking as the highest among the 11 features. Following closelywas the d-band center, which was presumed to exert influence on electrical conductivity and, consequently,adsorption properties. W ith 5-fold cross-validation using the Extra Tree accuracy, the 24-sample data set achieved an accuracy of 88%. The 72-sample data set achieved an a ccuracy of 78% using multilayerperceptron after 5-fold cross-vali dation, with both data sets exhibiting low standard deviations.”
      原文链接:
    • NETL
    • NSTL

    ShanghaiTech University Reports Findings in Machine Learning (Machine Learning on Microstructure-Property Relationship of Lithium-Ion Conducting Oxide Solid Ele ctrolytes)

    41-42页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Machine Learning is th e subject of a report. According to newsoriginating from Shanghai, People’s Rep ublic of China, by NewsRx correspondents, research stated, “Understandingthe st ructure-property relationship of lithium-ion conducting solid oxide electrolytes is essentialto accelerate their development and commercialization. However, th e structural complexity of nonidealmaterials increases the difficulty of study. ”Our news journalists obtained a quote from the research from ShanghaiTech Univer sity, “Here, wedevelop an algorithmic framework to understand the effect of mic rostructure on the properties by linkingthe microscopic morphology images to th eir ionic conductivities. We adopt garnet and perovskite polycrystallineoxides as examples and quantify the microscopic morphologies via extracting determined physicalparameters from the images. It directly visualizes the effect of physic al parameters on their correspondingionic conductivities. As a result, we can d etermine the microstructural features of a Li-ion conductor withhigh ionic cond uctivity, which can guide the synthesis of highly conductive solid electrolytes.”
      原文链接:
    • NETL
    • NSTL

    Reports from Johannes Kepler University Highlight Recent Findings in Robotics (Dedicated Dynamic Parameter Identification for Deltalike Robots)

    42-43页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators publish new report on Ro botics. According to news reporting out ofLinz, Austria, by NewsRx editors, res earch stated, “Dynamics simulation of parallel kinematic manipulators(PKM) and non-linear control methods require a precisely identified dynamics model and exp licitgeneralized mass matrix. Standard methods, which identify so-called dynami c base-parameters, are notsufficient to this end.”Financial support for this research came from LCM K2 Center for Symbiotic Mechat ronics.Our news journalists obtained a quote from the research from Johannes Kepler Uni versity, “Algorithmsfor identifying the complete set of dynamic parameters were proposed for serial manipulators. A dedicatedidentification method for PKM doe s not exist, however. Such a method is introduced here for the largeclass of De lta-like PKM exploiting the parallel structure and making use of model simplific ations specificto this class. The proposed method guarantees physical consisten cy of the identified parameters, and inparticular a positive definite generaliz ed mass matrix. The method is applied to a simulated model withexactly known pa rameters, which allows for verification of the obtained dynamic parameters. The resultsshow that the generalized mass matrix, the acceleration, and the Corioli s, gravitation and friction termsin the equations of motion (EOM) are well appr oximated. The second example is a real 4-DOF industrialDelta robot ABB IRB 360- 6/1600. For this robot, a physically consistent set of inertia and friction parameters is identified from measurements.”
      原文链接:
    • NETL
    • NSTL

    Investigators at Ecole de Technologie Superieure Discuss Findings in Robotics (Spherical Rolling Robots-design, Modeling, and Control: a Systematic Literature R eview)

    43-44页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - A new study on Robotics is now availab le. According to news originating from Montreal,Canada, by NewsRx correspondent s, research stated, “Spherical robots have garnered increasing interestfor thei r applications in exploration, tunnel inspection, and extraterrestrial missions. Diverse designs haveemerged, including barycentric configurations, pendulum -b ased mechanisms, etc.”Financial support for this research came from Natural Sciences and Engineering R esearch Council ofCanada (NSERC).Our news journalists obtained a quote from the research from Ecole de Technologi e Superieure, “Inaddition, a wide spectrum of control strategies has been propo sed, ranging from traditional PID approachesto cutting -edge neural networks. O ur systematic review aims to comprehensively identify and categorizelocomotion systems and control schemes employed by spherical robots, spanning the years 199 6 to 2023.A meticulous search across five databases yielded a dataset of 3199 r ecords. As a result of our exhaustiveanalysis, we identified a collection of no vel designs and control strategies. Leveraging the insights garnered,we provide valuable recommendations for optimizing the design and control aspects of spher ical robots,supporting both novel design endeavors and the advancement of field deployments.”
      原文链接:
    • NETL
    • NSTL

    Studies from University of Alcala Further Understanding of Robotics (Multisensory Integration for Topological Indoor Localization of Mobile Robots In Complex Symmetrical Environments)

    44-44页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Robotics is the subjec t of a report. According to news reportingoriginating in Madrid, Spain, by News Rx journalists, research stated, “Indoor localization is essentialfor robotic n avigation by using different sensors on board. Specifically, visual localization with a singlecamera is a great challenge in highly symmetric environments (e.g . offices, hospitals or residences), whereappearance patterns are repetitive an d captures from different locations provide very similar images.”Financial support for this research came from Spanish Government.The news reporters obtained a quote from the research from the University of Alc ala, “To overcomethis issue, in this paper, we present a method that integrates multisensory information from an RGB-Dcamera, a LiDAR and motor encoders. Our approach simultaneously utilizes spatial consistency from areference topologica l map and temporal consistency from time-series observations. Inspired by humancognitive perception, we define a two layered topological architecture that enco mpasses both coarseinformation of object distributions and structural informati on with some metric references. Categories ofcommon objects in the environments , such as fire extinguishers or doors, are used as natural beacons. Weevaluated our approach in two real-world buildings based on a multi-aisle structure with corridors of verysimilar appearance.”
      原文链接:
    • NETL
    • NSTL

    Shanghai University of Traditional Chinese Medicine Reports Findings in Mastitis (Prediction models for postoperative recurrence of non-lactating mastitis based on machine learning)

    45-46页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Breast Diseases and Co nditions - Mastitis is the subject of areport. According to news reporting orig inating from Shanghai, People’s Republic of China, by NewsRxcorrespondents, res earch stated, “This study aims to build a machine learning (ML) model to predictthe recurrence probability for postoperative non-lactating mastitis (NLM) by Ra ndom Forest (RF) andXGBoost algorithms. It can provide the ability to identify the risk of NLM recurrence and guidance inclinical treatment plan.”Funders for this research include National Natural Science Foundation of China Y outh IncubationProject of Shuguang Hospital affiliated Shanghai University of T raditional Chinese Medicine, ShanghaiMunicipal Health and Health Commission.
      原文链接:
    • NETL
    • NSTL

    Findings from Tsinghua University Update Understanding of Robotics (Fusednet: End-to-end Mobile Robot Relocalization In Dynamic Large-scale Scene)

    46-46页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - A new study on Robotics is now availab le. According to news reporting from Shenzhen,People’s Republic of China, by Ne wsRx journalists, research stated, “To improve robot relocalizationaccuracy in both static and dynamic environments, we introduce a novel network, FusedNet, wh ichincorporates a cross-attention to fuse global and local image features for e nd-to-end relocalization.”Financial support for this research came from Guangdong Natural Science Fund-Gen eral Programme.The news correspondents obtained a quote from the research from Tsinghua Univers ity, “This approachrelies solely on a monocular camera sensor that is fixed on the mobile robot, and directly predicts theabsolute pose from the input RGB ima ge. Additionally, we have collected a mobile robot relocalizationdataset, terme d moBotReloc, consisting of dynamic large-scale scenes, using the Unity 3D simul ationplatform and a real mobile robot.”According to the news reporters, the research concluded: “Through extensive expe riments on 7Scenesand moBotReloc, we demonstrate that FusedNet achieves signifi cant accuracy in 6-DoF camera relocalizationin static scenes, and exhibits supe rior relocalization performance in dynamic large-scale scenes formobile robot a pplications, outperforming existing end-to-end methods that rely solely on a sin gle globalor local feature.”
      原文链接:
    • NETL
    • NSTL

    Yuan Ze University Researcher Furthers Understanding of Machine Learning (Feature-Selection-Based DDoS Attack Detection Using AI Algorithms)

    47-47页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews - Data detailed on artificial intelligence have bee n presented. According to news originating fromTaoyuan, Taiwan, by NewsRx corre spondents, research stated, “SDN has the ability to transform networkdesign by providing increased versatility and effective regulation.”Funders for this research include Nstc.The news reporters obtained a quote from the research from Yuan Ze University: “ Its programmablecentralized controller gives network administration employees m ore authority, allowing for more seamlesssupervision. However, centralization m akes it vulnerable to a variety of attack vectors, with distributeddenial of se rvice (DDoS) attacks posing a serious concern. Feature selection-based Machine L earning(ML) techniques are more effective than traditional signature-based Intr usion Detection Systems (IDS) atidentifying new threats in the context of defen ding against distributed denial of service (DDoS) attacks.In this study, NGBoos t is compared with four additional machine learning (ML) algorithms: convolution alneural network (CNN), Stochastic Gradient Descent (SGD), Decision Tree, and R andom Forest, in orderto assess the effectiveness of DDoS detection on the CICD DoS2019 dataset. It focuses on importantmeasures such as F1 score, recall, accu racy, and precision. We have examined NeTBIOS, a layer-7 attack,and SYN, a laye r-4 attack, in our paper.”
      原文链接:
    • NETL
    • NSTL